Add first version of object detection

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+from PIL import Image, ImageDraw
+from transformers import DetrImageProcessor, DetrForObjectDetection
+import torch
+
+# Load DETR model and processor from Hugging Face
+model_name = "facebook/detr-resnet-50"
+processor = DetrImageProcessor.from_pretrained(model_name)
+model = DetrForObjectDetection.from_pretrained(model_name)
+
+# Main function: takes an image and returns it with boxes and labels
+def detect_objects(image):
+    inputs = processor(images=image, return_tensors="pt")
+    outputs = model(**inputs)
+
+    # Convert model output to usable detection results
+    target_sizes = torch.tensor([image.size[::-1]])
+    results = processor.post_process_object_detection(
+        outputs, threshold=0.9, target_sizes=target_sizes
+    )[0]
+
+    # Draw bounding boxes and labels on a copy of the image
+    image_with_boxes = image.copy()
+    draw = ImageDraw.Draw(image_with_boxes)
+    
+    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+        box = [round(x, 2) for x in box.tolist()]
+        draw.rectangle(box, outline="red", width=3)
+        label_text = f"{model.config.id2label[label.item()]}: {round(score.item(), 2)}"
+        draw.text((box[0], box[1]), label_text, fill="white")
+
+    return image_with_boxes
+
+# Gradio interface
+app = gr.Interface(
+    fn=detect_objects,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image()
+)
+
+# Run app
+if __name__ == "__main__":
+    app.launch()